© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11965
    Prev
    Next
    INDEX
    Explanations

    the use of emphasis or highlight annotation attributes in UI development

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Back
    -0.68
     back
    -0.64
    Back
    -0.60
    back
    -0.59
     BACK
    -0.52
    BACK
    -0.50
    Background
    -0.49
     fore
    -0.48
     background
    -0.46
     Therefore
    -0.46
    POSITIVE LOGITS
     foreground
    3.06
    foreground
    2.86
    Foreground
    1.41
     Vordergrund
    1.01
    ContentAsync
    0.81
     estimés
    0.75
    前景
    0.74
     forefront
    0.73
     onData
    0.72
    WithIOException
    0.71
    Activations Density 0.003%

    No Known Activations